Range interval optimization of prestressed anchors based on the least squares support vector machine and artificial fish swarm algorithm

The practical engineering of reinforced soil retaining walls in Jiehe Overpass,which locates on No.104 National Highway in Shandong Province of China,was taken as an example to determine the reasonable range interval of a prestressed anchor layout on the base of limited test data.Firstly,a nonlinear functional relation between the optimization parameters and optimization object was fitted by the least squares support vector machine(LSSVM).Then,the model was trained through data samples from in-situ test.Finally,the model was optimized by the artificial fish swarm algorithm(AFSA) to get the reasonable range interval,and the same time the rationality of optimization parameters was verified by monitoring the reinforcement effect of post-construction.The results show that this model is reasonable and feasible,with the characteristic of easily modeling,rapid convergence rate and high inversion accuracy.